
import os
import math
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from os.path import exists
import requests
from sklearn.preprocessing import OneHotEncoder, LabelEncoder
import random
from statsmodels.tsa.stattools import acf, pacf
from statsmodels.graphics.tsaplots import plot_acf, plot_pacf
from statsmodels.tsa.seasonal import seasonal_decompose
from statsmodels.tsa.stattools import adfuller
from statsmodels.tsa.arima.model import ARIMA
from statsmodels.tsa.arima.model import ARIMA
from statsmodels.tsa.statespace.sarimax import SARIMAX

from pmdarima.arima import auto_arima
from pmdarima.arima import ADFTest

from sklearn.metrics import mean_absolute_error, mean_squared_error, mean_absolute_percentage_error
from utils.metrics import evaluate


import pickle
import warnings
from math import sqrt

import matplotlib as mpl

import pmdarima as pm
import tensorflow as tf
import xgboost as xgb
from bayes_opt import BayesianOptimization
from prophet import Prophet
from matplotlib import pyplot as plt
from sklearn import linear_model, svm
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import make_scorer, mean_squared_error
from sklearn.model_selection import GridSearchCV, cross_val_score
from sklearn.neighbors import KNeighborsRegressor
from sklearn.preprocessing import StandardScaler
from statsmodels.tsa.ar_model import AR
from statsmodels.tsa.arima_model import ARIMA
from statsmodels.tsa.holtwinters import ExponentialSmoothing, SimpleExpSmoothing
from statsmodels.tsa.statespace.sarimax import SARIMAX
from tqdm import tqdm

#Importing libraries


if not exists('Rapporti_di_lavoro_attivati.csv'):
    file = requests.get("https://dati.lombardia.it/api/views/qbau-cyuc/rows.csv?accessType=DOWNLOAD", allow_redirects=True)
    open('Rapporti_di_lavoro_attivati.csv', 'wb').write(file.content)

if not exists('Rapporti_di_lavoro_cessati.csv'):
    file = requests.get("https://dati.lombardia.it/api/views/nwz3-p6vm/rows.csv?accessType=DOWNLOAD", allow_redirects=True)
    open('Rapporti_di_lavoro_cessati.csv', 'wb').write(file.content)


attivati = pd.read_csv('Rapporti_di_lavoro_attivati.csv')
cessati = pd.read_csv('Rapporti_di_lavoro_cessati.csv')
pil = pd.read_csv('PilRegioniIta.csv', encoding = 'latin')


pil.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 105 entries, 0 to 104
Data columns (total 3 columns):
 #   Column                  Non-Null Count  Dtype 
---  ------                  --------------  ----- 
 0   Anno                    105 non-null    int64 
 1   Regioni                 105 non-null    object
 2   P.I.L. Milioni di Euro  105 non-null    int64 
dtypes: int64(2), object(1)
memory usage: 2.6+ KB


pil.head()


attivati.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 9579794 entries, 0 to 9579793
Data columns (total 9 columns):
 #   Column                     Dtype 
---  ------                     ----- 
 0   DATA                       object
 1   GENERE                     object
 2   ETA                        int64 
 3   SETTOREECONOMICODETTAGLIO  object
 4   TITOLOSTUDIO               object
 5   CONTRATTO                  object
 6   MODALITALAVORO             object
 7   PROVINCIAIMPRESA           object
 8   ITALIANO                   object
dtypes: int64(1), object(8)
memory usage: 657.8+ MB


attivati.head()


cessati.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 3741394 entries, 0 to 3741393
Data columns (total 9 columns):
 #   Column                     Dtype 
---  ------                     ----- 
 0   DATA                       object
 1   GENERE                     object
 2   ETA                        int64 
 3   SETTOREECONOMICODETTAGLIO  object
 4   TITOLOSTUDIO               object
 5   CONTRATTO                  object
 6   MODALITALAVORO             object
 7   PROVINCIAIMPRESA           object
 8   ITALIANO                   object
dtypes: int64(1), object(8)
memory usage: 256.9+ MB


cessati.head()


attivati.loc[:,'DATA'] = pd.to_datetime(attivati.loc[:,'DATA'], format="%d/%m/%Y", errors='coerce')
cessati.loc[:,'DATA'] = pd.to_datetime(cessati.loc[:,'DATA'], format="%d/%m/%Y", errors='coerce')
pil.loc[:,'Anno'] = pd.to_datetime(pil.loc[:,'Anno'], format='%Y', errors='coerce')

pil


prov = pil.iloc[:-1]


prov.head(10)


plt.figure(figsize=(15,8))
sns.lineplot(data=prov, x='Anno',y='P.I.L. Milioni di Euro', hue='Regioni',linewidth = 4.0) #show PIL for each major region

<AxesSubplot:xlabel='Anno', ylabel='P.I.L. Milioni di Euro'>


pil.isnull().sum() #no null values check

Anno                      0
Regioni                   0
P.I.L. Milioni di Euro    0
dtype: int64


#remove regions that are not 'lombardia', because our study revolves around the Lombardia records
pil = pil[pil['Regioni'] == 'Lombardia']
pil = pil.loc[:, ['Anno', 'P.I.L. Milioni di Euro',]] #we remove the Regioni attribute because we only have Lombardia wich is a obvious information

pil


pil.info() #correctly converted to dateTime

<class 'pandas.core.frame.DataFrame'>
Int64Index: 22 entries, 2 to 104
Data columns (total 2 columns):
 #   Column                  Non-Null Count  Dtype         
---  ------                  --------------  -----         
 0   Anno                    22 non-null     datetime64[ns]
 1   P.I.L. Milioni di Euro  22 non-null     int64         
dtypes: datetime64[ns](1), int64(1)
memory usage: 528.0 bytes


pil.index = pil.Anno
pilgg = pil.copy()


pilgg.index = pd.DatetimeIndex(pilgg['Anno']).year #year as index to perform operations on dates and ts analyisi


pilgg2 = pilgg.copy()
pilgg2.drop(columns='Anno', inplace = True)
pilgg2


kwsne = dict(marker='o')
pilgg2.plot(figsize =(15,6),**kwsne, linewidth = 3.0)


attivati


copia = attivati.copy() #copy for activation dataset


copia.isna().sum()[copia.isna().sum()>0].plot(kind='bar') #null values insection for activated contracts

<AxesSubplot:>


len(copia)

9579794


aipoc= cessati.copy() #copy for terminated dataset
aipoc


aipoc.isna().sum()[aipoc.isna().sum()>0].plot(kind='bar') #null values inspection for terminated contracts

<AxesSubplot:>


len(aipoc)

3741394


copia.drop(columns = ['MODALITALAVORO', 'TITOLOSTUDIO', 'ITALIANO', 'PROVINCIAIMPRESA'], inplace = True)
aipoc.drop(columns=['MODALITALAVORO', 'TITOLOSTUDIO', 'ITALIANO', 'PROVINCIAIMPRESA'], inplace = True)


copia.isnull().sum()

DATA                            0
GENERE                          0
ETA                             0
SETTOREECONOMICODETTAGLIO    2888
CONTRATTO                       0
dtype: int64


aipoc.isnull().sum()

DATA                            1
GENERE                          0
ETA                             0
SETTOREECONOMICODETTAGLIO    1019
CONTRATTO                       0
dtype: int64


copia.dropna(inplace=True)
aipoc.dropna(inplace=True)


copia.isnull().sum() #null value check after cleaning the activated contracts dataset

DATA                         0
GENERE                       0
ETA                          0
SETTOREECONOMICODETTAGLIO    0
CONTRATTO                    0
dtype: int64


aipoc.isnull().sum() #null value check after cleaning the terminated contracts dataset

DATA                         0
GENERE                       0
ETA                          0
SETTOREECONOMICODETTAGLIO    0
CONTRATTO                    0
dtype: int64


copia.index = copia['DATA']
aipoc.index = aipoc['DATA']
#creation of a new column for the major datasets with copy of date


copiafilt = copia.copy()
copiafilt['STATO'] = 1
copiafilt


aipocfilt = aipoc.copy()
aipocfilt['STATO'] = 0
aipocfilt


dFrames = [copiafilt,aipocfilt]
unifDf = pd.concat(dFrames)
#merge of the two dataset in one; the datasets have the same attributes so it will be easier to do filtering and cleaning operations once they have been merged together


unifDf


unifDf.loc[(unifDf['GENERE'] == 'M'), 'GENERE'] = 1
unifDf.loc[(unifDf['GENERE'] == 'F'), 'GENERE'] = 0
copiaEpic = unifDf
copiaEpic
#genere to 1 for males and 0 for females


copiaEpicFilt = copiaEpic.copy()


copiaEpicFilt['Mese'] = copiaEpicFilt['DATA'].dt.month
copiaEpicFilt['Anno'] = copiaEpicFilt['DATA'].dt.year
#estrapolating year and month from the dates


copiaEpicFilt


mergedData = pd.merge(copiaEpicFilt, pilgg2, how = 'inner', on = 'Anno')
#merging dataframes with pil dataset


mergedData


mergedDataCopy = mergedData.copy()


mergedDataCopy.sort_values('DATA', inplace=True)


mergedDataCopy.index = mergedDataCopy['DATA']


mergedDataCopy.rename(columns = {'DATA':'DATE','SETTOREECONOMICODETTAGLIO' : 'SETTORE',
                                 'Mese' : 'MESE', 'Anno' : 'ANNO', 'P.I.L. Milioni di Euro' : 'PIL MLN EUR ANNUO' }, inplace=True)


transField = LabelEncoder().fit_transform(mergedDataCopy.SETTORE)
transCon = LabelEncoder().fit_transform(mergedDataCopy.CONTRATTO)
mergedDataCopy['SETT_ID'] = transField
mergedDataCopy['CONTR_N'] = transCon
mergedDataCopy.head()


columns_titles = ['CONTRATTO','CONTR_N', 'SETTORE', 'SETT_ID' , 'STATO',
                  'ETA', 'GENERE', 'DATE', 'MESE', 'ANNO', 'PIL MLN EUR ANNUO']
mergedDataCopy = mergedDataCopy.reindex(columns=columns_titles)
mergedDataCopy
#reordering the dataset


dfOrdinato = mergedDataCopy.copy()
dfOrdinato


fig, (ax1, ax2) = plt.subplots(1,2, figsize=(20,8))
sns.boxplot(x = dfOrdinato['ETA'].loc[dfOrdinato['STATO'] == 1], ax=ax1)
sns.boxplot(x = dfOrdinato['ETA'].loc[dfOrdinato['STATO'] == 0], ax=ax2)
plt.show()
#lets clean age. We have ages that are not particoularly suitable for our analysis


etaDaDropp = dfOrdinato[(dfOrdinato.ETA >= 18) & (dfOrdinato.ETA <= 67) &
                        (dfOrdinato['DATE'].dt.year>2009 ) & (dfOrdinato['DATE'].dt.year<2022)]
#range di interesse di età per un contratto lavorativo che possa essere rilevante nella media legale
#range di interesse per anni in cui la digitalizzazione e i social hanno incominciato a segnare un'evoluzione nel mondo del lavoro


etaDaDropp


cleanData = etaDaDropp.copy()


dfOrdAtt = cleanData.loc[cleanData['STATO'] == 1]
dfOrdCess = cleanData.loc[cleanData['STATO'] == 0]
#grouping activated and terminated contracts to perform analysis


dfOrdAtt


dfOrdCess


fig, (ax1, ax2) = plt.subplots(1,2, figsize=(20,8))
sns.boxplot(x = dfOrdAtt['ETA'], ax=ax1)
sns.boxplot(x = dfOrdCess['ETA'], ax=ax2)
plt.show()


dfOrdAtt.isnull().sum()

CONTRATTO            0
CONTR_N              0
SETTORE              0
SETT_ID              0
STATO                0
ETA                  0
GENERE               0
DATE                 0
MESE                 0
ANNO                 0
PIL MLN EUR ANNUO    0
dtype: int64


dfOrdCess.isnull().sum()

CONTRATTO            0
CONTR_N              0
SETTORE              0
SETT_ID              0
STATO                0
ETA                  0
GENERE               0
DATE                 0
MESE                 0
ANNO                 0
PIL MLN EUR ANNUO    0
dtype: int64


dfOrdAtt.value_counts('SETTORE') #settori più importanti per attivazioni

SETTORE
Alberghi                                                                           437403
Ristorazione con somministrazione                                                  424929
Attività di produzione cinematografica, di video e di programmi televisivi         355267
Attività di famiglie e convivenze come datori di lavoro per personale domestico    326150
Altri servizi di supporto alle imprese nca                                         281581
                                                                                    ...  
Agenti e rappresentanti di giocattoli                                                   1
Attività delle guide alpine                                                             1
Coltivazione di fiori in colture protette fuori suolo                                   1
Allevamento di cammelli e camelidi                                                      1
Gestione di stazioni per autobus                                                        1
Length: 1224, dtype: int64


aa = dfOrdAtt.groupby('SETTORE').count().sort_values(by = 'CONTRATTO', ascending=False)
aa


perAtt = aa.head(10)


dfOrdCess.value_counts('SETTORE') #settori più importanti per cessazioni

SETTORE
Attività di famiglie e convivenze come datori di lavoro per personale domestico                                                      258683
Ristorazione con somministrazione                                                                                                    202637
Costruzione di edifici residenziali e non residenziali                                                                               171079
Pulizia generale (non specializzata) di edifici                                                                                      145277
Altri servizi di supporto alle imprese nca                                                                                           143166
                                                                                                                                      ...  
Gestione di stazioni per autobus                                                                                                          1
Fabbricazione di altri prodotti petroliferi raffinati                                                                                     1
Commercio all'ingrosso di tabacco grezzo                                                                                                  1
Agenti e rappresentanti di pellicce                                                                                                       1
Commercio al dettaglio di spaghi, cordami, tele e sacchi di juta e prodotti per l'imballaggio (esclusi quelli in carta e cartone)         1
Length: 1205, dtype: int64


ab = dfOrdCess.groupby('SETTORE').count().sort_values(by = 'CONTRATTO', ascending=False)
ab


perCess = ab.head(10)


perAtt = perAtt.loc[:, ['STATO',]]
perAtt['CESSAZIONI'] = ab['STATO'].loc[ab.index.isin(perAtt.index.tolist())]
perAtt.rename(columns = {'STATO' : 'ATTIVAZIONI'}, inplace = True)


perAtt


perCess = perCess.loc[:, ['STATO',]]
perCess['ATTIVAZIONI'] = aa['STATO'].loc[aa.index.isin(perCess.index.tolist())]
perCess.rename(columns = {'STATO' : 'CESSAZIONI'}, inplace = True)


perCess


ax = perAtt.plot.bar(width = 0.6, figsize = (15,6))
#plot attivazioni più rilevanti


#plt.ticklabel_format(style='plain')
counts=dfOrdAtt.loc[:, ['SETTORE']].value_counts() 
counts=counts.head(10)
pltfigsize=(20,15)
plt.figure(figsize=pltfigsize) 
plt.ticklabel_format(style='plain') #Importante lasciare qui questo comando 
plt.barh(y=[i[0] for i in counts.index], width=counts.values, color='green')
plt.title('Numero di contratti attivati per settore')
plt.xlabel('CONTRATTI ATTIVATI')
plt.ylabel('SETTORE')

Text(0, 0.5, 'SETTORE')


 #visualizing percentage of activated contracts for genre
 
# Creating dataset
geners = dfOrdAtt.GENERE.value_counts()

data = geners.values
indx = geners.index
 
 
# Creating explode data
explode = (0.1, 0.0)
 
# Creating color parameters
colors = ( "blue", "red")
 
# Wedge properties
wp = { 'linewidth' : 1, 'edgecolor' : "black" }
 
# Creating autocpt arguments
def func(pct, allvalues):
    absolute = int(pct / 100.*np.sum(allvalues))
    return "{:.1f}%\n({:d})".format(pct, absolute)
 
# Creating plot
fig, ax = plt.subplots(figsize =(10, 7))
wedges, texts, autotexts = ax.pie(data,
                                  autopct = lambda pct: func(pct, data),
                                  explode = explode,
                                  labels = indx,
                                  shadow = True,
                                  colors = colors,
                                  startangle = 90,
                                  wedgeprops = wp,
                                  textprops = dict(color ="white"))
 
# Adding legend
ax.legend(wedges, indx,
          title ="Genere: 1 = Male,  0 = Female",
          loc ="center left",
          bbox_to_anchor =(1, 0, 0.5, 1))
 
plt.setp(autotexts, size = 8, weight ="bold")
ax.set_title("Pie chart genere attivazioni")
 
# show plot
plt.show()


value_count_modalita = dfOrdAtt.loc[:, ['ANNO']].value_counts()
plt.ticklabel_format(style='plain')
abscissa_axis=value_count_modalita.index
ordinate_axis=value_count_modalita.values
ax=value_count_modalita.plot.bar(x=abscissa_axis,y=ordinate_axis,color='orange', figsize = (18,9))
plt.title('Numero di contratti attivati per Anno')
plt.xlabel('ANNI DI RIFERIMENTO')
plt.ylabel('NUMERO ATTIVAZIONI')

Text(0, 0.5, 'NUMERO ATTIVAZIONI')


ax = perCess.plot.bar(width = 0.6, figsize = (15,6), color = ['red','green'])
    
#plot cessazioni più rilevanti


#plt.ticklabel_format(style='plain')
counts=dfOrdCess.loc[:, ['SETTORE']].value_counts() 
counts=counts.head(10)
pltfigsize=(20,15)
plt.figure(figsize=pltfigsize) 
plt.ticklabel_format(style='plain') #Importante lasciare qui questo comando 
plt.barh(y=[i[0] for i in counts.index], width=counts.values, color='red')
plt.title('Numero di contratti cessati per settore')
plt.xlabel('CONTRATTI CESSATI')
plt.ylabel('SETTORE')

Text(0, 0.5, 'SETTORE')


 #visualizing percentage of activated contracts for genre

 
 
# Creating dataset
geners = dfOrdCess.GENERE.value_counts()

data = geners.values
indx = geners.index
 
 
# Creating explode data
explode = (0.1, 0.0)
 
# Creating color parameters
colors = ( "orange", "pink")
 
# Wedge properties
wp = { 'linewidth' : 1, 'edgecolor' : "black" }
 
# Creating autocpt arguments
def func(pct, allvalues):
    absolute = int(pct / 100.*np.sum(allvalues))
    return "{:.1f}%\n({:d})".format(pct, absolute)
 
# Creating plot
fig, ax = plt.subplots(figsize =(10, 7))
wedges, texts, autotexts = ax.pie(data,
                                  autopct = lambda pct: func(pct, data),
                                  explode = explode,
                                  labels = indx,
                                  shadow = True,
                                  colors = colors,
                                  startangle = 90,
                                  wedgeprops = wp,
                                  textprops = dict(color ="black"))
 
# Adding legend
ax.legend(wedges, indx,
          title ="Genere: 1 = Male,  0 = Female",
          loc ="center left",
          bbox_to_anchor =(1, 0, 0.5, 1))
 
plt.setp(autotexts, size = 8, weight ="bold")
ax.set_title("Pie chart genere cessazioni")
 
# show plot
plt.show()


value_count_modalita = dfOrdCess.loc[:, ['ANNO']].value_counts()
plt.ticklabel_format(style='plain')
abscissa_axis=value_count_modalita.index
ordinate_axis=value_count_modalita.values
ax=value_count_modalita.plot.bar(x=abscissa_axis,y=ordinate_axis,color='red', figsize = (18,9))
plt.title('Numero di contratti cessati per anno')
plt.xlabel('ANNI DI RIFERIMENTO')
plt.ylabel('NUMERO CESSAZIONI')

Text(0, 0.5, 'NUMERO CESSAZIONI')


sns.set(rc={"figure.figsize":(25,15)})
plt.subplot(3,3,2)
sns.histplot(dfOrdAtt.DATE,label="DATA",stat="density",bins=10,kde=True, color="orange").set_title("Distrubuzione contratti attivati negli anni", color = 'green')
plt.subplot(3,3,3)
sns.histplot(dfOrdCess.DATE,label="DATA",stat="density",bins=10,kde=True, color="orange").set_title("Distribuzione contratti cessati negli anni", color = 'red')

Text(0.5, 1.0, 'Distribuzione contratti cessati negli anni')


attivHead = dfOrdAtt.loc[dfOrdAtt['SETTORE'].isin(perAtt.index)]


cessHead = dfOrdCess.loc[dfOrdCess['SETTORE'].isin(perCess.index)]


cessHead['SETTORE'].value_counts()

Attività di famiglie e convivenze come datori di lavoro per personale domestico    258683
Ristorazione con somministrazione                                                  202637
Costruzione di edifici residenziali e non residenziali                             171079
Pulizia generale (non specializzata) di edifici                                    145277
Altri servizi di supporto alle imprese nca                                         143166
Trasporto di merci su strada                                                        86094
Bar e altri esercizi simili senza cucina                                            85297
Servizi logistici relativi alla distribuzione delle merci                           69199
Alberghi                                                                            61989
Movimento merci relativo ad altri trasporti terrestri                               56825
Name: SETTORE, dtype: int64


mostA = aa.head(10).index.tolist()
mostA


mostC = ab.head(10).index.tolist()
mostC


li = mostA
li2 = mostC


dfAttivatiMost = pd.DataFrame(columns=[li]) #da rinominare dfAttivatiMost
for k in li:
     a = dfOrdAtt.loc[(dfOrdAtt['SETTORE'] == k)].ANNO.value_counts()
     dfAttivatiMost[k] = a
dfAttivatiMost.sort_index(inplace= True)


dfAttivatiMost


dfAttivatiMost.iloc[:, 0:4].plot.bar() #plot 4 most important activated contracts per year
plt.legend(title = 'Four most important activated labours')

<matplotlib.legend.Legend at 0x229c65104f0>


dfAttivatiMost['PIL_MLN_EUR'] = pilgg2['P.I.L. Milioni di Euro']


dfAttivatiMost


corr = dfAttivatiMost.corr()
sns.set_theme (style = 'white')
heatmap = sns.heatmap(corr, annot = True)
plt.title('Lombardia : most important activated labours')

Text(0.5, 1.0, 'Lombardia : most important activated labours')


dfAttivatiMost.boxplot(vert = False) #boxplot most important activated contracts

<AxesSubplot:>


dfCessatiMost = pd.DataFrame(columns=[li2])
for c in li2:
     t = dfOrdCess.loc[(dfOrdCess['SETTORE'] == c)].ANNO.value_counts()
     dfCessatiMost[c] = t
dfCessatiMost.sort_index(inplace= True)


dfCessatiMost


dfCessatiMost.iloc[:, 0:4].plot.bar()  #plot 4 most imprtant ceased contracts per year
plt.legend(title = 'Four most important ceased labours')

<matplotlib.legend.Legend at 0x229df1be3a0>


dfCessatiMost['PIL_MLN_EUR'] = pilgg2['P.I.L. Milioni di Euro']


dfCessatiMost


corr2 = dfCessatiMost.corr()
sns.set_theme (style = 'white')
heatmap2 = sns.heatmap(corr2, annot = True)
plt.title('Lombardia : most important ceased labours')

Text(0.5, 1.0, 'Lombardia : most important ceased labours')


dfCessatiMost.boxplot(vert = False) #boxplot most ceased contracts

<AxesSubplot:>


attFrames = []
for val in perAtt.index:  #visualize 
     na = attivHead.loc[(attivHead['SETTORE'] == val)]
     h = na.resample('M').count()
     attFrames.append(h)
     na2 = h.rename (columns = {'SETTORE' :
     ('ATTIVAZIONI: '+ val)}).loc[:, ['ATTIVAZIONI: '+ val,]]
     na2.plot(color=np.random.rand(3,), legend = val, figsize = (20,10))
     fig, axes = plt.subplots(1,2,figsize=(20,6), dpi= 120)
     plot_acf(h.SETTORE.tolist(), lags=50, ax=axes[0],
     title =  'Acr: ' + val)
     plot_pacf(h.SETTORE.tolist(), lags=50, ax=axes[1],
     title = 'Partial acr: '+ val)
     plt.show()

c:\Users\ggudy\anaconda3\envs\ProgettoUni\lib\site-packages\statsmodels\graphics\tsaplots.py:348: FutureWarning: The default method 'yw' can produce PACF values outside of the [-1,1] interval. After 0.13, the default will change tounadjusted Yule-Walker ('ywm'). You can use this method now by setting method='ywm'.
  warnings.warn(

c:\Users\ggudy\anaconda3\envs\ProgettoUni\lib\site-packages\statsmodels\graphics\tsaplots.py:348: FutureWarning: The default method 'yw' can produce PACF values outside of the [-1,1] interval. After 0.13, the default will change tounadjusted Yule-Walker ('ywm'). You can use this method now by setting method='ywm'.
  warnings.warn(

c:\Users\ggudy\anaconda3\envs\ProgettoUni\lib\site-packages\statsmodels\graphics\tsaplots.py:348: FutureWarning: The default method 'yw' can produce PACF values outside of the [-1,1] interval. After 0.13, the default will change tounadjusted Yule-Walker ('ywm'). You can use this method now by setting method='ywm'.
  warnings.warn(

c:\Users\ggudy\anaconda3\envs\ProgettoUni\lib\site-packages\statsmodels\graphics\tsaplots.py:348: FutureWarning: The default method 'yw' can produce PACF values outside of the [-1,1] interval. After 0.13, the default will change tounadjusted Yule-Walker ('ywm'). You can use this method now by setting method='ywm'.
  warnings.warn(

c:\Users\ggudy\anaconda3\envs\ProgettoUni\lib\site-packages\statsmodels\graphics\tsaplots.py:348: FutureWarning: The default method 'yw' can produce PACF values outside of the [-1,1] interval. After 0.13, the default will change tounadjusted Yule-Walker ('ywm'). You can use this method now by setting method='ywm'.
  warnings.warn(

c:\Users\ggudy\anaconda3\envs\ProgettoUni\lib\site-packages\statsmodels\graphics\tsaplots.py:348: FutureWarning: The default method 'yw' can produce PACF values outside of the [-1,1] interval. After 0.13, the default will change tounadjusted Yule-Walker ('ywm'). You can use this method now by setting method='ywm'.
  warnings.warn(

c:\Users\ggudy\anaconda3\envs\ProgettoUni\lib\site-packages\statsmodels\graphics\tsaplots.py:348: FutureWarning: The default method 'yw' can produce PACF values outside of the [-1,1] interval. After 0.13, the default will change tounadjusted Yule-Walker ('ywm'). You can use this method now by setting method='ywm'.
  warnings.warn(

c:\Users\ggudy\anaconda3\envs\ProgettoUni\lib\site-packages\statsmodels\graphics\tsaplots.py:348: FutureWarning: The default method 'yw' can produce PACF values outside of the [-1,1] interval. After 0.13, the default will change tounadjusted Yule-Walker ('ywm'). You can use this method now by setting method='ywm'.
  warnings.warn(

c:\Users\ggudy\anaconda3\envs\ProgettoUni\lib\site-packages\statsmodels\graphics\tsaplots.py:348: FutureWarning: The default method 'yw' can produce PACF values outside of the [-1,1] interval. After 0.13, the default will change tounadjusted Yule-Walker ('ywm'). You can use this method now by setting method='ywm'.
  warnings.warn(

c:\Users\ggudy\anaconda3\envs\ProgettoUni\lib\site-packages\statsmodels\graphics\tsaplots.py:348: FutureWarning: The default method 'yw' can produce PACF values outside of the [-1,1] interval. After 0.13, the default will change tounadjusted Yule-Walker ('ywm'). You can use this method now by setting method='ywm'.
  warnings.warn(


attFrames

[            CONTRATTO  CONTR_N  SETTORE  SETT_ID  STATO   ETA  GENERE  DATE  \
 DATA                                                                          
 2010-01-31       3767     3767     3767     3767   3767  3767    3767  3767   
 2010-02-28       3592     3592     3592     3592   3592  3592    3592  3592   
 2010-03-31       3528     3528     3528     3528   3528  3528    3528  3528   
 2010-04-30       3293     3293     3293     3293   3293  3293    3293  3293   
 2010-05-31       3823     3823     3823     3823   3823  3823    3823  3823   
 ...               ...      ...      ...      ...    ...   ...     ...   ...   
 2021-08-31        789      789      789      789    789   789     789   789   
 2021-09-30       1174     1174     1174     1174   1174  1174    1174  1174   
 2021-10-31       1337     1337     1337     1337   1337  1337    1337  1337   
 2021-11-30        946      946      946      946    946   946     946   946   
 2021-12-31        782      782      782      782    782   782     782   782   
 
             MESE  ANNO  PIL MLN EUR ANNUO  
 DATA                                       
 2010-01-31  3767  3767               3767  
 2010-02-28  3592  3592               3592  
 2010-03-31  3528  3528               3528  
 2010-04-30  3293  3293               3293  
 2010-05-31  3823  3823               3823  
 ...          ...   ...                ...  
 2021-08-31   789   789                789  
 2021-09-30  1174  1174               1174  
 2021-10-31  1337  1337               1337  
 2021-11-30   946   946                946  
 2021-12-31   782   782                782  
 
 [144 rows x 11 columns],
             CONTRATTO  CONTR_N  SETTORE  SETT_ID  STATO   ETA  GENERE  DATE  \
 DATA                                                                          
 2010-01-31       2254     2254     2254     2254   2254  2254    2254  2254   
 2010-02-28       2139     2139     2139     2139   2139  2139    2139  2139   
 2010-03-31       1869     1869     1869     1869   1869  1869    1869  1869   
 2010-04-30       1867     1867     1867     1867   1867  1867    1867  1867   
 2010-05-31       2054     2054     2054     2054   2054  2054    2054  2054   
 ...               ...      ...      ...      ...    ...   ...     ...   ...   
 2021-08-31       2016     2016     2016     2016   2016  2016    2016  2016   
 2021-09-30       2401     2401     2401     2401   2401  2401    2401  2401   
 2021-10-31       2467     2467     2467     2467   2467  2467    2467  2467   
 2021-11-30       2042     2042     2042     2042   2042  2042    2042  2042   
 2021-12-31       1796     1796     1796     1796   1796  1796    1796  1796   
 
             MESE  ANNO  PIL MLN EUR ANNUO  
 DATA                                       
 2010-01-31  2254  2254               2254  
 2010-02-28  2139  2139               2139  
 2010-03-31  1869  1869               1869  
 2010-04-30  1867  1867               1867  
 2010-05-31  2054  2054               2054  
 ...          ...   ...                ...  
 2021-08-31  2016  2016               2016  
 2021-09-30  2401  2401               2401  
 2021-10-31  2467  2467               2467  
 2021-11-30  2042  2042               2042  
 2021-12-31  1796  1796               1796  
 
 [144 rows x 11 columns],
             CONTRATTO  CONTR_N  SETTORE  SETT_ID  STATO   ETA  GENERE  DATE  \
 DATA                                                                          
 2010-01-31       1908     1908     1908     1908   1908  1908    1908  1908   
 2010-02-28       1933     1933     1933     1933   1933  1933    1933  1933   
 2010-03-31       1938     1938     1938     1938   1938  1938    1938  1938   
 2010-04-30       1687     1687     1687     1687   1687  1687    1687  1687   
 2010-05-31       2180     2180     2180     2180   2180  2180    2180  2180   
 ...               ...      ...      ...      ...    ...   ...     ...   ...   
 2021-08-31       2910     2910     2910     2910   2910  2910    2910  2910   
 2021-09-30       2836     2836     2836     2836   2836  2836    2836  2836   
 2021-10-31       2061     2061     2061     2061   2061  2061    2061  2061   
 2021-11-30       2192     2192     2192     2192   2192  2192    2192  2192   
 2021-12-31       2861     2861     2861     2861   2861  2861    2861  2861   
 
             MESE  ANNO  PIL MLN EUR ANNUO  
 DATA                                       
 2010-01-31  1908  1908               1908  
 2010-02-28  1933  1933               1933  
 2010-03-31  1938  1938               1938  
 2010-04-30  1687  1687               1687  
 2010-05-31  2180  2180               2180  
 ...          ...   ...                ...  
 2021-08-31  2910  2910               2910  
 2021-09-30  2836  2836               2836  
 2021-10-31  2061  2061               2061  
 2021-11-30  2192  2192               2192  
 2021-12-31  2861  2861               2861  
 
 [144 rows x 11 columns],
             CONTRATTO  CONTR_N  SETTORE  SETT_ID  STATO   ETA  GENERE  DATE  \
 DATA                                                                          
 2010-01-31       3039     3039     3039     3039   3039  3039    3039  3039   
 2010-02-28       2658     2658     2658     2658   2658  2658    2658  2658   
 2010-03-31       2591     2591     2591     2591   2591  2591    2591  2591   
 2010-04-30       2532     2532     2532     2532   2532  2532    2532  2532   
 2010-05-31       2374     2374     2374     2374   2374  2374    2374  2374   
 ...               ...      ...      ...      ...    ...   ...     ...   ...   
 2021-08-31       1853     1853     1853     1853   1853  1853    1853  1853   
 2021-09-30       1927     1927     1927     1927   1927  1927    1927  1927   
 2021-10-31       1560     1560     1560     1560   1560  1560    1560  1560   
 2021-11-30       1501     1501     1501     1501   1501  1501    1501  1501   
 2021-12-31       1712     1712     1712     1712   1712  1712    1712  1712   
 
             MESE  ANNO  PIL MLN EUR ANNUO  
 DATA                                       
 2010-01-31  3039  3039               3039  
 2010-02-28  2658  2658               2658  
 2010-03-31  2591  2591               2591  
 2010-04-30  2532  2532               2532  
 2010-05-31  2374  2374               2374  
 ...          ...   ...                ...  
 2021-08-31  1853  1853               1853  
 2021-09-30  1927  1927               1927  
 2021-10-31  1560  1560               1560  
 2021-11-30  1501  1501               1501  
 2021-12-31  1712  1712               1712  
 
 [144 rows x 11 columns],
             CONTRATTO  CONTR_N  SETTORE  SETT_ID  STATO   ETA  GENERE  DATE  \
 DATA                                                                          
 2010-01-31       3855     3855     3855     3855   3855  3855    3855  3855   
 2010-02-28       3368     3368     3368     3368   3368  3368    3368  3368   
 2010-03-31       2864     2864     2864     2864   2864  2864    2864  2864   
 2010-04-30       3157     3157     3157     3157   3157  3157    3157  3157   
 2010-05-31       2976     2976     2976     2976   2976  2976    2976  2976   
 ...               ...      ...      ...      ...    ...   ...     ...   ...   
 2021-08-31       1028     1028     1028     1028   1028  1028    1028  1028   
 2021-09-30        948      948      948      948    948   948     948   948   
 2021-10-31        991      991      991      991    991   991     991   991   
 2021-11-30        712      712      712      712    712   712     712   712   
 2021-12-31        878      878      878      878    878   878     878   878   
 
             MESE  ANNO  PIL MLN EUR ANNUO  
 DATA                                       
 2010-01-31  3855  3855               3855  
 2010-02-28  3368  3368               3368  
 2010-03-31  2864  2864               2864  
 2010-04-30  3157  3157               3157  
 2010-05-31  2976  2976               2976  
 ...          ...   ...                ...  
 2021-08-31  1028  1028               1028  
 2021-09-30   948   948                948  
 2021-10-31   991   991                991  
 2021-11-30   712   712                712  
 2021-12-31   878   878                878  
 
 [144 rows x 11 columns],
             CONTRATTO  CONTR_N  SETTORE  SETT_ID  STATO   ETA  GENERE  DATE  \
 DATA                                                                          
 2010-01-31       1433     1433     1433     1433   1433  1433    1433  1433   
 2010-02-28       1425     1425     1425     1425   1425  1425    1425  1425   
 2010-03-31       1382     1382     1382     1382   1382  1382    1382  1382   
 2010-04-30       1729     1729     1729     1729   1729  1729    1729  1729   
 2010-05-31       1480     1480     1480     1480   1480  1480    1480  1480   
 ...               ...      ...      ...      ...    ...   ...     ...   ...   
 2021-08-31       2033     2033     2033     2033   2033  2033    2033  2033   
 2021-09-30       1844     1844     1844     1844   1844  1844    1844  1844   
 2021-10-31       1317     1317     1317     1317   1317  1317    1317  1317   
 2021-11-30       1844     1844     1844     1844   1844  1844    1844  1844   
 2021-12-31       2277     2277     2277     2277   2277  2277    2277  2277   
 
             MESE  ANNO  PIL MLN EUR ANNUO  
 DATA                                       
 2010-01-31  1433  1433               1433  
 2010-02-28  1425  1425               1425  
 2010-03-31  1382  1382               1382  
 2010-04-30  1729  1729               1729  
 2010-05-31  1480  1480               1480  
 ...          ...   ...                ...  
 2021-08-31  2033  2033               2033  
 2021-09-30  1844  1844               1844  
 2021-10-31  1317  1317               1317  
 2021-11-30  1844  1844               1844  
 2021-12-31  2277  2277               2277  
 
 [144 rows x 11 columns],
             CONTRATTO  CONTR_N  SETTORE  SETT_ID  STATO   ETA  GENERE  DATE  \
 DATA                                                                          
 2010-01-31       1002     1002     1002     1002   1002  1002    1002  1002   
 2010-02-28       1455     1455     1455     1455   1455  1455    1455  1455   
 2010-03-31       1642     1642     1642     1642   1642  1642    1642  1642   
 2010-04-30       1554     1554     1554     1554   1554  1554    1554  1554   
 2010-05-31        694      694      694      694    694   694     694   694   
 ...               ...      ...      ...      ...    ...   ...     ...   ...   
 2021-08-31       1683     1683     1683     1683   1683  1683    1683  1683   
 2021-09-30       1744     1744     1744     1744   1744  1744    1744  1744   
 2021-10-31       1718     1718     1718     1718   1718  1718    1718  1718   
 2021-11-30       1491     1491     1491     1491   1491  1491    1491  1491   
 2021-12-31       1287     1287     1287     1287   1287  1287    1287  1287   
 
             MESE  ANNO  PIL MLN EUR ANNUO  
 DATA                                       
 2010-01-31  1002  1002               1002  
 2010-02-28  1455  1455               1455  
 2010-03-31  1642  1642               1642  
 2010-04-30  1554  1554               1554  
 2010-05-31   694   694                694  
 ...          ...   ...                ...  
 2021-08-31  1683  1683               1683  
 2021-09-30  1744  1744               1744  
 2021-10-31  1718  1718               1718  
 2021-11-30  1491  1491               1491  
 2021-12-31  1287  1287               1287  
 
 [144 rows x 11 columns],
             CONTRATTO  CONTR_N  SETTORE  SETT_ID  STATO   ETA  GENERE  DATE  \
 DATA                                                                          
 2010-01-31       2202     2202     2202     2202   2202  2202    2202  2202   
 2010-02-28       1679     1679     1679     1679   1679  1679    1679  1679   
 2010-03-31       1646     1646     1646     1646   1646  1646    1646  1646   
 2010-04-30       1532     1532     1532     1532   1532  1532    1532  1532   
 2010-05-31       1777     1777     1777     1777   1777  1777    1777  1777   
 ...               ...      ...      ...      ...    ...   ...     ...   ...   
 2021-08-31       1629     1629     1629     1629   1629  1629    1629  1629   
 2021-09-30       1561     1561     1561     1561   1561  1561    1561  1561   
 2021-10-31       1202     1202     1202     1202   1202  1202    1202  1202   
 2021-11-30       1253     1253     1253     1253   1253  1253    1253  1253   
 2021-12-31       1370     1370     1370     1370   1370  1370    1370  1370   
 
             MESE  ANNO  PIL MLN EUR ANNUO  
 DATA                                       
 2010-01-31  2202  2202               2202  
 2010-02-28  1679  1679               1679  
 2010-03-31  1646  1646               1646  
 2010-04-30  1532  1532               1532  
 2010-05-31  1777  1777               1777  
 ...          ...   ...                ...  
 2021-08-31  1629  1629               1629  
 2021-09-30  1561  1561               1561  
 2021-10-31  1202  1202               1202  
 2021-11-30  1253  1253               1253  
 2021-12-31  1370  1370               1370  
 
 [144 rows x 11 columns],
             CONTRATTO  CONTR_N  SETTORE  SETT_ID  STATO   ETA  GENERE  DATE  \
 DATA                                                                          
 2010-01-31        497      497      497      497    497   497     497   497   
 2010-02-28        418      418      418      418    418   418     418   418   
 2010-03-31        497      497      497      497    497   497     497   497   
 2010-04-30        607      607      607      607    607   607     607   607   
 2010-05-31        644      644      644      644    644   644     644   644   
 ...               ...      ...      ...      ...    ...   ...     ...   ...   
 2021-08-31        257      257      257      257    257   257     257   257   
 2021-09-30       1462     1462     1462     1462   1462  1462    1462  1462   
 2021-10-31       2235     2235     2235     2235   2235  2235    2235  2235   
 2021-11-30       4060     4060     4060     4060   4060  4060    4060  4060   
 2021-12-31       1357     1357     1357     1357   1357  1357    1357  1357   
 
             MESE  ANNO  PIL MLN EUR ANNUO  
 DATA                                       
 2010-01-31   497   497                497  
 2010-02-28   418   418                418  
 2010-03-31   497   497                497  
 2010-04-30   607   607                607  
 2010-05-31   644   644                644  
 ...          ...   ...                ...  
 2021-08-31   257   257                257  
 2021-09-30  1462  1462               1462  
 2021-10-31  2235  2235               2235  
 2021-11-30  4060  4060               4060  
 2021-12-31  1357  1357               1357  
 
 [144 rows x 11 columns],
             CONTRATTO  CONTR_N  SETTORE  SETT_ID  STATO   ETA  GENERE  DATE  \
 DATA                                                                          
 2010-01-31       1251     1251     1251     1251   1251  1251    1251  1251   
 2010-02-28       1463     1463     1463     1463   1463  1463    1463  1463   
 2010-03-31       1704     1704     1704     1704   1704  1704    1704  1704   
 2010-04-30       1160     1160     1160     1160   1160  1160    1160  1160   
 2010-05-31        855      855      855      855    855   855     855   855   
 ...               ...      ...      ...      ...    ...   ...     ...   ...   
 2021-08-31        948      948      948      948    948   948     948   948   
 2021-09-30       1073     1073     1073     1073   1073  1073    1073  1073   
 2021-10-31       1219     1219     1219     1219   1219  1219    1219  1219   
 2021-11-30        667      667      667      667    667   667     667   667   
 2021-12-31        759      759      759      759    759   759     759   759   
 
             MESE  ANNO  PIL MLN EUR ANNUO  
 DATA                                       
 2010-01-31  1251  1251               1251  
 2010-02-28  1463  1463               1463  
 2010-03-31  1704  1704               1704  
 2010-04-30  1160  1160               1160  
 2010-05-31   855   855                855  
 ...          ...   ...                ...  
 2021-08-31   948   948                948  
 2021-09-30  1073  1073               1073  
 2021-10-31  1219  1219               1219  
 2021-11-30   667   667                667  
 2021-12-31   759   759                759  
 
 [144 rows x 11 columns]]


len(attFrames[0])

144


cessFrames = []
for val in perCess.index:
     na = cessHead.loc[(cessHead['SETTORE'] == val)]
     h = na.resample('M').count()
     cessFrames.append(h)
     na2 = h.rename (columns = {'SETTORE' :
     ('CESSAZIONI: '+ val)}).loc[:, ['CESSAZIONI: '+ val,]]
     na2.plot(color=np.random.rand(3,), legend = val, figsize = (20,10))
     fig, axes = plt.subplots(1,2,figsize=(20,6), dpi= 120)
     plot_acf(h.SETTORE.tolist(), lags=50, ax=axes[0],
     title =  'Acr: ' + val)
     plot_pacf(h.SETTORE.tolist(), lags=50, ax=axes[1],
     title = 'Partial acr: '+ val)
     plt.show()

c:\Users\ggudy\anaconda3\envs\ProgettoUni\lib\site-packages\statsmodels\graphics\tsaplots.py:348: FutureWarning: The default method 'yw' can produce PACF values outside of the [-1,1] interval. After 0.13, the default will change tounadjusted Yule-Walker ('ywm'). You can use this method now by setting method='ywm'.
  warnings.warn(

c:\Users\ggudy\anaconda3\envs\ProgettoUni\lib\site-packages\statsmodels\graphics\tsaplots.py:348: FutureWarning: The default method 'yw' can produce PACF values outside of the [-1,1] interval. After 0.13, the default will change tounadjusted Yule-Walker ('ywm'). You can use this method now by setting method='ywm'.
  warnings.warn(

c:\Users\ggudy\anaconda3\envs\ProgettoUni\lib\site-packages\statsmodels\graphics\tsaplots.py:348: FutureWarning: The default method 'yw' can produce PACF values outside of the [-1,1] interval. After 0.13, the default will change tounadjusted Yule-Walker ('ywm'). You can use this method now by setting method='ywm'.
  warnings.warn(

c:\Users\ggudy\anaconda3\envs\ProgettoUni\lib\site-packages\statsmodels\graphics\tsaplots.py:348: FutureWarning: The default method 'yw' can produce PACF values outside of the [-1,1] interval. After 0.13, the default will change tounadjusted Yule-Walker ('ywm'). You can use this method now by setting method='ywm'.
  warnings.warn(

c:\Users\ggudy\anaconda3\envs\ProgettoUni\lib\site-packages\statsmodels\graphics\tsaplots.py:348: FutureWarning: The default method 'yw' can produce PACF values outside of the [-1,1] interval. After 0.13, the default will change tounadjusted Yule-Walker ('ywm'). You can use this method now by setting method='ywm'.
  warnings.warn(

c:\Users\ggudy\anaconda3\envs\ProgettoUni\lib\site-packages\statsmodels\graphics\tsaplots.py:348: FutureWarning: The default method 'yw' can produce PACF values outside of the [-1,1] interval. After 0.13, the default will change tounadjusted Yule-Walker ('ywm'). You can use this method now by setting method='ywm'.
  warnings.warn(

c:\Users\ggudy\anaconda3\envs\ProgettoUni\lib\site-packages\statsmodels\graphics\tsaplots.py:348: FutureWarning: The default method 'yw' can produce PACF values outside of the [-1,1] interval. After 0.13, the default will change tounadjusted Yule-Walker ('ywm'). You can use this method now by setting method='ywm'.
  warnings.warn(

c:\Users\ggudy\anaconda3\envs\ProgettoUni\lib\site-packages\statsmodels\graphics\tsaplots.py:348: FutureWarning: The default method 'yw' can produce PACF values outside of the [-1,1] interval. After 0.13, the default will change tounadjusted Yule-Walker ('ywm'). You can use this method now by setting method='ywm'.
  warnings.warn(

c:\Users\ggudy\anaconda3\envs\ProgettoUni\lib\site-packages\statsmodels\graphics\tsaplots.py:348: FutureWarning: The default method 'yw' can produce PACF values outside of the [-1,1] interval. After 0.13, the default will change tounadjusted Yule-Walker ('ywm'). You can use this method now by setting method='ywm'.
  warnings.warn(

c:\Users\ggudy\anaconda3\envs\ProgettoUni\lib\site-packages\statsmodels\graphics\tsaplots.py:348: FutureWarning: The default method 'yw' can produce PACF values outside of the [-1,1] interval. After 0.13, the default will change tounadjusted Yule-Walker ('ywm'). You can use this method now by setting method='ywm'.
  warnings.warn(


totaliAttivatiTs = dfOrdAtt.copy()


totaliCessatiTs = dfOrdCess.copy()


attAnnuali = totaliAttivatiTs.resample('Y').count().iloc[:, [2]]
cessAnnuali = totaliCessatiTs.resample('Y').count().iloc[:, [2]]
attAnnuali.rename(columns={'SETTORE': 'N.ATTIVATI'}, inplace=True)
cessAnnuali.rename(columns={'SETTORE': 'N.CESSATI'}, inplace=True)
ax = attAnnuali.plot(kind="bar", color = "orange")
cessAnnuali.plot( kind="bar", ax=ax, color="red")

<AxesSubplot:xlabel='DATA'>


attTimeSe = totaliAttivatiTs.resample('M').count().iloc[:, [2]]
cessTimeSe = totaliCessatiTs.resample('M').count().iloc[:, [2]]
attTimeSe.rename(columns={'SETTORE': 'N.ATTIVATI'}, inplace=True)
cessTimeSe.rename(columns={'SETTORE': 'N.CESSATI'}, inplace=True)


attTimeSe.plot()

<AxesSubplot:xlabel='DATA'>


plot_pacf(attTimeSe)

c:\Users\ggudy\anaconda3\envs\ProgettoUni\lib\site-packages\statsmodels\graphics\tsaplots.py:348: FutureWarning: The default method 'yw' can produce PACF values outside of the [-1,1] interval. After 0.13, the default will change tounadjusted Yule-Walker ('ywm'). You can use this method now by setting method='ywm'.
  warnings.warn(


cgs =attTimeSe
analysis = cgs['N.ATTIVATI'].copy()


decompose_result_mult = seasonal_decompose(analysis, model="multiplicative")

trend = decompose_result_mult.trend
seasonal = decompose_result_mult.seasonal
residual = decompose_result_mult.resid

decompose_result_mult.plot();


# Additive decomposition
decadd = seasonal_decompose(analysis, model="additive")
add = decadd.plot()
plt.show()


toStation = analysis.diff().dropna()
plt.figure(figsize=(12,5))
ax1 = toStation.plot()
ax1.set_xlabel("Date")
ax1.set_ylabel("Count")
plt.grid(True)
plt.show()


test_result=adfuller(attTimeSe['N.ATTIVATI'])
def adfuller_test(vls):
    result=adfuller(vls)
    labels = ['ADF Test Statistic','p-value','#Lags Used','Number of Observations']
    for value,label in zip(result,labels):
        print(label+' : '+str(value) )

if test_result[1] <= 0.05:
    print("strong evidence against the null hypothesis(Ho),result < 0.05, reject the null hypothesis. Data is stationary")
else:
    print("weak evidence against null hypothesis, result > 0,05, indicating it is non-stationary ")

adfuller_test(attTimeSe['N.ATTIVATI'])

weak evidence against null hypothesis, result > 0,05, indicating it is non-stationary 
ADF Test Statistic : -0.8645322360982132
p-value : 0.7994280243739811
#Lags Used : 10
Number of Observations : 133


attTimeSe['Difference'] = attTimeSe['N.ATTIVATI'] - attTimeSe['N.ATTIVATI'].shift(1)
attTimeSe['Seasonal First Difference']=attTimeSe['N.ATTIVATI']-attTimeSe['N.ATTIVATI'].shift(12)
attTimeSe.head()


# Again testing if data is stationary
adfuller_test(attTimeSe['Seasonal First Difference'].dropna())

ADF Test Statistic : -2.719896118345244
p-value : 0.07065819658515171
#Lags Used : 11
Number of Observations : 120


tfram2 = attTimeSe['N.ATTIVATI']


tfram2

DATA
2010-01-31    61434
2010-02-28    55401
2010-03-31    57889
2010-04-30    57900
2010-05-31    59538
              ...  
2021-08-31    59683
2021-09-30    55403
2021-10-31    47578
2021-11-30    54033
2021-12-31    55282
Freq: M, Name: N.ATTIVATI, Length: 144, dtype: int64


stepwise_model = auto_arima(tfram2, start_p=1, start_q=1,
                           max_p=3, max_q=3, m=12,
                           start_P=0, seasonal=True, #non stationary ts requires seasonality capturing mechanism
                           d=1, D=1, trace=True,
                           error_action='ignore',  
                           suppress_warnings=True, 
                           stepwise=True)
print(stepwise_model.aic())

Performing stepwise search to minimize aic
 ARIMA(1,1,1)(0,1,1)[12]             : AIC=2876.339, Time=0.43 sec
 ARIMA(0,1,0)(0,1,0)[12]             : AIC=2963.621, Time=0.02 sec
 ARIMA(1,1,0)(1,1,0)[12]             : AIC=2925.239, Time=0.15 sec
 ARIMA(0,1,1)(0,1,1)[12]             : AIC=2876.769, Time=0.18 sec
 ARIMA(1,1,1)(0,1,0)[12]             : AIC=2919.553, Time=0.14 sec
 ARIMA(1,1,1)(1,1,1)[12]             : AIC=2878.262, Time=0.53 sec
 ARIMA(1,1,1)(0,1,2)[12]             : AIC=2878.235, Time=1.05 sec
 ARIMA(1,1,1)(1,1,0)[12]             : AIC=2897.925, Time=0.53 sec
 ARIMA(1,1,1)(1,1,2)[12]             : AIC=inf, Time=3.32 sec
 ARIMA(1,1,0)(0,1,1)[12]             : AIC=2901.961, Time=0.17 sec
 ARIMA(2,1,1)(0,1,1)[12]             : AIC=2859.754, Time=0.33 sec
 ARIMA(2,1,1)(0,1,0)[12]             : AIC=2906.863, Time=0.13 sec
 ARIMA(2,1,1)(1,1,1)[12]             : AIC=2860.501, Time=0.44 sec
 ARIMA(2,1,1)(0,1,2)[12]             : AIC=2860.152, Time=0.85 sec
 ARIMA(2,1,1)(1,1,0)[12]             : AIC=2885.464, Time=0.28 sec
 ARIMA(2,1,1)(1,1,2)[12]             : AIC=2861.562, Time=1.23 sec
 ARIMA(2,1,0)(0,1,1)[12]             : AIC=2864.032, Time=0.43 sec
 ARIMA(3,1,1)(0,1,1)[12]             : AIC=2861.740, Time=0.54 sec
 ARIMA(2,1,2)(0,1,1)[12]             : AIC=2863.856, Time=0.41 sec
 ARIMA(1,1,2)(0,1,1)[12]             : AIC=2878.226, Time=0.28 sec
 ARIMA(3,1,0)(0,1,1)[12]             : AIC=2858.875, Time=0.32 sec
 ARIMA(3,1,0)(0,1,0)[12]             : AIC=2904.559, Time=0.11 sec
 ARIMA(3,1,0)(1,1,1)[12]             : AIC=2859.467, Time=0.46 sec
 ARIMA(3,1,0)(0,1,2)[12]             : AIC=2859.107, Time=0.66 sec
 ARIMA(3,1,0)(1,1,0)[12]             : AIC=2883.872, Time=0.24 sec
 ARIMA(3,1,0)(1,1,2)[12]             : AIC=2860.639, Time=1.14 sec
 ARIMA(3,1,0)(0,1,1)[12] intercept   : AIC=2860.049, Time=0.64 sec

Best model:  ARIMA(3,1,0)(0,1,1)[12]          
Total fit time: 15.024 seconds
2858.8751711603436


fig = stepwise_model.plot_diagnostics()
fig.set_size_inches(18.5, 10.5, forward=True)
plt.show()


# Train Test Split Index
train_size = 0.88
split_idx = round(len(tfram2)* train_size)
split_idx

# Split
train = tfram2.iloc[:split_idx]
test = tfram2.iloc[split_idx:]

# Visualize split
fig,ax= plt.subplots(figsize=(12,8))
kws = dict(marker='o')
plt.plot(train, label='Train', **kws)
plt.plot(test, label='Test', **kws)
ax.legend(bbox_to_anchor=[1,1]);


stepwise_model.fit(train)

ARIMA(order=(3, 1, 0), scoring_args={}, seasonal_order=(0, 1, 1, 12),
      suppress_warnings=True, with_intercept=False)


future_forecast, cf = stepwise_model.predict(n_periods=17, return_conf_int=True)


future_forecast = pd.DataFrame(future_forecast,index = test.index, columns=['Prediction'])


kwsnep = dict(marker='o')
cc = pd.concat([test,future_forecast],axis=1)
cc.plot(**kwsnep, figsize=(20, 10))

<AxesSubplot:xlabel='DATA'>


index_of_fc = pd.date_range(tfram2.index[-1], periods = 17, freq='MS')

future_forecast_3 = future_forecast
future_forecast_3 = future_forecast_3.set_index(index_of_fc)

# Plot Della prediction 
plt.figure(figsize=(25, 15))
kwsn = dict(marker='o')
plt.plot(tfram2, color='blue', label='Actual Date', **kwsn)
plt.plot(future_forecast_3, color='red', label='Predict', **kwsn)
plt.legend(loc='lower right', fontsize=15)
plt.title("Predizione attivati")
plt.show()


mape = mean_absolute_percentage_error(test, future_forecast_3.Prediction)
print(mape)

0.1433354671416055


MSE = mean_squared_error(test, future_forecast_3)
RMSE = math.sqrt(MSE)
print('The mean square error is: ', MSE)
print('The Root Mean Square error is: ', RMSE)

The mean square error is:  118219597.59521176
The Root Mean Square error is:  10872.883591541471


cessTimeSe.plot()

<AxesSubplot:xlabel='DATA'>


plot_acf(cessTimeSe)


analysis = cessTimeSe['N.CESSATI'].copy()


decompose_result_mult = seasonal_decompose(analysis, model="multiplicative")

trend = decompose_result_mult.trend
seasonal = decompose_result_mult.seasonal
residual = decompose_result_mult.resid

decompose_result_mult.plot();


# Additive decomposition
decadd = seasonal_decompose(analysis, model="additive")
add = decadd.plot()
plt.show()


toStation = analysis.diff().dropna()
plt.figure(figsize=(12,5))
ax1 = toStation.plot()
ax1.set_xlabel("Date")
ax1.set_ylabel("Count")
plt.grid(True)
plt.show()


test_result=adfuller(cessTimeSe['N.CESSATI'])
adfuller_test(cessTimeSe['N.CESSATI'])

ADF Test Statistic : 0.29783007172434917
p-value : 0.9772447120881198
#Lags Used : 11
Number of Observations : 132


cessTimeSe['Difference'] = cessTimeSe['N.CESSATI'] - cessTimeSe['N.CESSATI'].shift(1)
cessTimeSe['Seasonal First Difference']=cessTimeSe['N.CESSATI']-cessTimeSe['N.CESSATI'].shift(12)
cessTimeSe.head()


adfuller_test(cessTimeSe['Seasonal First Difference'].dropna())

ADF Test Statistic : -2.1073010143852637
p-value : 0.2415889796826256
#Lags Used : 11
Number of Observations : 120


tfram3 = cessTimeSe['N.CESSATI']


stepwise_model2 = auto_arima(tfram3, start_p=1, start_q=1,
                           max_p=3, max_q=3, m=12,
                           start_P=0, seasonal=True,
                           d=1, D=1, trace=True,
                           error_action='ignore',  
                           suppress_warnings=True, 
                           stepwise=True)
print(stepwise_model2.aic())

Performing stepwise search to minimize aic
 ARIMA(1,1,1)(0,1,1)[12]             : AIC=2640.572, Time=0.35 sec
 ARIMA(0,1,0)(0,1,0)[12]             : AIC=2752.956, Time=0.03 sec
 ARIMA(1,1,0)(1,1,0)[12]             : AIC=2699.760, Time=0.13 sec
 ARIMA(0,1,1)(0,1,1)[12]             : AIC=2637.125, Time=0.46 sec
 ARIMA(0,1,1)(0,1,0)[12]             : AIC=2677.337, Time=0.06 sec
 ARIMA(0,1,1)(1,1,1)[12]             : AIC=2641.473, Time=0.68 sec
 ARIMA(0,1,1)(0,1,2)[12]             : AIC=2641.425, Time=1.62 sec
 ARIMA(0,1,1)(1,1,0)[12]             : AIC=2657.064, Time=0.26 sec
 ARIMA(0,1,1)(1,1,2)[12]             : AIC=2639.874, Time=1.18 sec
 ARIMA(0,1,0)(0,1,1)[12]             : AIC=inf, Time=0.48 sec
 ARIMA(0,1,2)(0,1,1)[12]             : AIC=2652.470, Time=0.29 sec
 ARIMA(1,1,0)(0,1,1)[12]             : AIC=2678.273, Time=0.16 sec
 ARIMA(1,1,2)(0,1,1)[12]             : AIC=2629.745, Time=1.07 sec
 ARIMA(1,1,2)(0,1,0)[12]             : AIC=2668.670, Time=0.33 sec
 ARIMA(1,1,2)(1,1,1)[12]             : AIC=2633.823, Time=1.54 sec
 ARIMA(1,1,2)(0,1,2)[12]             : AIC=2655.123, Time=1.85 sec
 ARIMA(1,1,2)(1,1,0)[12]             : AIC=2643.399, Time=0.98 sec
 ARIMA(1,1,2)(1,1,2)[12]             : AIC=inf, Time=2.83 sec
 ARIMA(2,1,2)(0,1,1)[12]             : AIC=2641.895, Time=0.48 sec
 ARIMA(1,1,3)(0,1,1)[12]             : AIC=2629.152, Time=1.64 sec
 ARIMA(1,1,3)(0,1,0)[12]             : AIC=2666.158, Time=0.21 sec
 ARIMA(1,1,3)(1,1,1)[12]             : AIC=2639.457, Time=1.70 sec
 ARIMA(1,1,3)(0,1,2)[12]             : AIC=2646.939, Time=3.58 sec
 ARIMA(1,1,3)(1,1,0)[12]             : AIC=2654.086, Time=0.66 sec
 ARIMA(1,1,3)(1,1,2)[12]             : AIC=inf, Time=3.58 sec
 ARIMA(0,1,3)(0,1,1)[12]             : AIC=2651.763, Time=0.35 sec
 ARIMA(2,1,3)(0,1,1)[12]             : AIC=inf, Time=1.69 sec
 ARIMA(1,1,3)(0,1,1)[12] intercept   : AIC=2652.016, Time=0.59 sec

Best model:  ARIMA(1,1,3)(0,1,1)[12]          
Total fit time: 28.788 seconds
2629.1524349926863


fig = stepwise_model2.plot_diagnostics()
fig.set_size_inches(18.5, 10.5, forward=True)
plt.show()


# Train Test Split Index
train_size = 0.85
split_idx = round(len(tfram3)* train_size)
split_idx

# Split
train2 = tfram3.iloc[:split_idx]
test2 = tfram3.iloc[split_idx:]

# Visualize split
fig,ax= plt.subplots(figsize=(12,8))
kws = dict(marker='o')
plt.plot(train2, label='Train', **kws)
plt.plot(test2, label='Test', **kws)
ax.legend(bbox_to_anchor=[1,1]);


stepwise_model2.fit(train2)

ARIMA(order=(1, 1, 3), scoring_args={}, seasonal_order=(0, 1, 1, 12),
      suppress_warnings=True, with_intercept=False)


future, cf2 = stepwise_model2.predict(n_periods=22, return_conf_int=True)


future = pd.DataFrame(future,index = test2.index, columns=['Prediction'])


cc = pd.concat([test2,future],axis=1)
cc.plot(**kwsnep, figsize=(20, 10))

<AxesSubplot:xlabel='DATA'>


index_of = pd.date_range(tfram3.index[-1], periods = 22, freq='MS')

future_forecast_4 = future
future_forecast_4 = future_forecast_4.set_index(index_of)

# Plot Della prediction 
plt.figure(figsize=(25, 15))
plt.plot(tfram3, color='blue', label='Actual Date', **kwsn)
plt.plot(future_forecast_4, color='red', label='Predict', **kwsn)
plt.legend(loc='lower right', fontsize=15)
plt.title("Predizione cessati")
plt.show()


mape = mean_absolute_percentage_error(test2, future_forecast_4.Prediction)
print(mape)

0.2081571585254859


MSE = mean_squared_error(test2, future_forecast_4)
RMSE = math.sqrt(MSE)
print('The mean square error is: ', MSE)
print('The Root Mean Square error is: ', RMSE)

The mean square error is:  26336112.14437239
The Root Mean Square error is:  5131.872187065105


attFrames[1].sum()

CONTRATTO            424929
CONTR_N              424929
SETTORE              424929
SETT_ID              424929
STATO                424929
ETA                  424929
GENERE               424929
DATE                 424929
MESE                 424929
ANNO                 424929
PIL MLN EUR ANNUO    424929
dtype: int64


#raggruppo per giorno le attivazioni del settore ristorazione


ristorazioneDaily = dfOrdAtt.loc[dfOrdAtt['SETTORE'] == 'Ristorazione con somministrazione']


ristorazioneDaily = ristorazioneDaily.resample('D').count().iloc[:, [2]]
ristorazioneDaily.rename(columns={'SETTORE': 'VALUES'}, inplace=True)


ristorazioneDaily.plot()

<AxesSubplot:xlabel='DATA'>


resultsDict = {}
predictionsDict = {}

split_date = '2020-08-30'
df_training = ristorazioneDaily.loc[ristorazioneDaily.index <= split_date]
df_test = ristorazioneDaily.loc[ristorazioneDaily.index > split_date]
print(f"{len(df_training)} days of training data \n {len(df_test)} days of testing data ")

3894 days of training data 
 466 days of testing data


# Walk throught the test data, training and predicting 1 day ahead for all the test data
index = len(df_training)
yhat = list()
for t in tqdm(range(len(df_test.VALUES))):
    temp_train = ristorazioneDaily[:len(df_training)+t]
    model = SimpleExpSmoothing(temp_train.VALUES)
    model_fit = model.fit()
    predictions = model_fit.predict(start=len(temp_train), end=len(temp_train))
    yhat = yhat + [predictions]

yhat = pd.concat(yhat)
resultsDict['SES'] = evaluate(df_test.VALUES, yhat.values)
predictionsDict['SES'] = yhat.values

100%|██████████| 466/466 [00:12<00:00, 37.04it/s]


# Walk throught the test data, training and predicting 1 day ahead for all the test data
index = len(df_training)
yhat = list()
for t in tqdm(range(len(df_test.VALUES))):
    temp_train = ristorazioneDaily[:len(df_training)+t]
    model = ExponentialSmoothing(temp_train.VALUES)
    model_fit = model.fit()
    predictions = model_fit.predict(start=len(temp_train), end=len(temp_train))
    yhat = yhat + [predictions]

yhat = pd.concat(yhat)
resultsDict['HWES'] = evaluate(df_test.VALUES, yhat.values)
predictionsDict['HWES'] = yhat.values

100%|██████████| 466/466 [00:12<00:00, 36.15it/s]


# ARIMA example

# Walk throught the test data, training and predicting 1 day ahead for all the test data
index = len(df_training)
yhat = list()
for t in tqdm(range(len(df_test.VALUES))):
    temp_train = ristorazioneDaily[:len(df_training)+t]
    model = ARIMA(temp_train.VALUES, order=(1, 0, 0))
    model_fit = model.fit()
    predictions = model_fit.predict(
        start=len(temp_train), end=len(temp_train), dynamic=False)
    yhat = yhat + [predictions]

yhat = pd.concat(yhat)
resultsDict['ARIMA'] = evaluate(df_test.VALUES, yhat.values)
predictionsDict['ARIMA'] = yhat.values

100%|██████████| 466/466 [02:24<00:00,  3.23it/s]


plt.plot(df_test.VALUES.values, label='Original')
plt.plot(yhat.values, color='red', label='ARIMA predicted')
plt.legend()

<matplotlib.legend.Legend at 0x229f7292190>


autoModel = pm.auto_arima(df_training.VALUES, trace=True,
                          error_action='ignore', suppress_warnings=True, seasonal=False)
autoModel.fit(df_training.VALUES)

Performing stepwise search to minimize aic
 ARIMA(2,1,2)(0,0,0)[0] intercept   : AIC=50357.270, Time=1.99 sec
 ARIMA(0,1,0)(0,0,0)[0] intercept   : AIC=51832.790, Time=0.16 sec
 ARIMA(1,1,0)(0,0,0)[0] intercept   : AIC=51038.821, Time=0.49 sec
 ARIMA(0,1,1)(0,0,0)[0] intercept   : AIC=50536.689, Time=1.53 sec
 ARIMA(0,1,0)(0,0,0)[0]             : AIC=51830.790, Time=0.10 sec
 ARIMA(1,1,2)(0,0,0)[0] intercept   : AIC=50462.312, Time=1.60 sec
 ARIMA(2,1,1)(0,0,0)[0] intercept   : AIC=50416.693, Time=1.14 sec
 ARIMA(3,1,2)(0,0,0)[0] intercept   : AIC=50357.102, Time=3.77 sec
 ARIMA(3,1,1)(0,0,0)[0] intercept   : AIC=inf, Time=6.98 sec
 ARIMA(4,1,2)(0,0,0)[0] intercept   : AIC=50344.113, Time=4.48 sec
 ARIMA(4,1,1)(0,0,0)[0] intercept   : AIC=50346.996, Time=3.79 sec
 ARIMA(5,1,2)(0,0,0)[0] intercept   : AIC=50346.064, Time=9.60 sec
 ARIMA(4,1,3)(0,0,0)[0] intercept   : AIC=50346.013, Time=6.42 sec
 ARIMA(3,1,3)(0,0,0)[0] intercept   : AIC=50353.639, Time=6.93 sec
 ARIMA(5,1,1)(0,0,0)[0] intercept   : AIC=50348.158, Time=4.17 sec
 ARIMA(5,1,3)(0,0,0)[0] intercept   : AIC=inf, Time=13.01 sec
 ARIMA(4,1,2)(0,0,0)[0]             : AIC=50342.115, Time=2.39 sec
 ARIMA(3,1,2)(0,0,0)[0]             : AIC=50355.105, Time=1.74 sec
 ARIMA(4,1,1)(0,0,0)[0]             : AIC=50344.999, Time=1.89 sec
 ARIMA(5,1,2)(0,0,0)[0]             : AIC=50344.065, Time=7.81 sec
 ARIMA(4,1,3)(0,0,0)[0]             : AIC=50344.014, Time=4.17 sec
 ARIMA(3,1,1)(0,0,0)[0]             : AIC=inf, Time=6.43 sec
 ARIMA(3,1,3)(0,0,0)[0]             : AIC=50351.642, Time=3.05 sec
 ARIMA(5,1,1)(0,0,0)[0]             : AIC=50346.161, Time=2.16 sec
 ARIMA(5,1,3)(0,0,0)[0]             : AIC=inf, Time=8.43 sec

Best model:  ARIMA(4,1,2)(0,0,0)[0]          
Total fit time: 104.299 seconds

ARIMA(order=(4, 1, 2), scoring_args={}, suppress_warnings=True,
      with_intercept=False)


order = autoModel.order
yhat = list()
for t in tqdm(range(len(df_test.VALUES))):
    temp_train = ristorazioneDaily[:len(df_training)+t]
    model = ARIMA(temp_train.VALUES, order=order)
    model_fit = model.fit()
    predictions = model_fit.predict(
        start=len(temp_train), end=len(temp_train), dynamic=False)
    yhat = yhat + [predictions]

yhat = pd.concat(yhat)
resultsDict['AutoARIMA {0}'.format(order)] = evaluate(
    df_test.VALUES, yhat)
predictionsDict['AutoARIMA {0}'.format(order)] = yhat.values

100%|██████████| 466/466 [18:47<00:00,  2.42s/it]


plt.plot(df_test.VALUES.values, label='Original')
plt.plot(yhat.values, color='red', label='AutoARIMA {0}'.format(order))
plt.legend()

<matplotlib.legend.Legend at 0x22c47b6a490>


# SARIMA example

# Walk throught the test data, training and predicting 1 day ahead for all the test data
index = len(df_training)
yhat = list()
for t in tqdm(range(len(df_test.VALUES))):
    temp_train = ristorazioneDaily[:len(df_training)+t]
    model = SARIMAX(temp_train.VALUES, order=(
        1, 0, 0), seasonal_order=(0, 0, 0, 3))
    model_fit = model.fit(disp=False)
    predictions = model_fit.predict(
        start=len(temp_train), end=len(temp_train), dynamic=False)
    yhat = yhat + [predictions]

yhat = pd.concat(yhat)
resultsDict['SARIMAX'] = evaluate(df_test.VALUES, yhat.values)
predictionsDict['SARIMAX'] = yhat.values

100%|██████████| 466/466 [00:56<00:00,  8.18it/s]


plt.plot(df_test.VALUES.values, label='Original')
plt.plot(yhat.values, color='red', label='SARIMAX')
plt.legend()

<matplotlib.legend.Legend at 0x229f721d700>


# Prophet needs some specifics data stuff, coment it here
prophet_training = df_training.rename(
    columns={'VALUES': 'y'})  # old method
prophet_training['ds'] = prophet_training.index
prophet_training.index = pd.RangeIndex(len(prophet_training.index))

prophet_test = df_test.rename(columns={'VALUES': 'y'})  # old method
prophet_test['ds'] = prophet_test.index
prophet_test.index = pd.RangeIndex(len(prophet_test.index))


prophet = Prophet(
    growth='linear',
    seasonality_mode='multiplicative',
    holidays_prior_scale=20,
    weekly_seasonality=False,
    daily_seasonality= True,
    yearly_seasonality=False
).add_seasonality(
    name='monthly',
    period=30.5,
    fourier_order=55
).add_seasonality(
    name='daily',
    period=1,
    fourier_order=15
).add_seasonality(
    name='weekly',
    period=7,
    fourier_order=25
).add_seasonality(
    name='yearly',
    period=365.25,
    fourier_order=20
).add_seasonality(
    name='quarterly',
    period=365.25/4,
    fourier_order=55
).add_country_holidays(country_name='Italy')


prophet.fit(prophet_training)
yhat = prophet.predict(prophet_test)
resultsDict['Prophet univariate'] = evaluate(
    df_test.VALUES, yhat.yhat.values)
predictionsDict['Prophet univariate'] = yhat.yhat.values

c:\Users\ggudy\anaconda3\envs\ProgettoUni\lib\site-packages\prophet\forecaster.py:896: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.
  components = components.append(new_comp)
c:\Users\ggudy\anaconda3\envs\ProgettoUni\lib\site-packages\prophet\forecaster.py:896: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.
  components = components.append(new_comp)
c:\Users\ggudy\anaconda3\envs\ProgettoUni\lib\site-packages\prophet\forecaster.py:896: FutureWarning: The frame.append method is deprecated and will be removed from pandas in a future version. Use pandas.concat instead.
  components = components.append(new_comp)


plt.plot(df_test.VALUES.values, label='Original')
plt.plot(yhat.yhat, color='red', label='Prophet univariate')
plt.legend()

<matplotlib.legend.Legend at 0x22c810a8fa0>


# ADD time features to our model
def create_time_features(df, target=None):
    """
    Creates time series features from datetime index
    """
    df['date'] = df.index
    df['quarter'] = df['date'].dt.quarter
    df['month'] = df['date'].dt.month
    df['year'] = df['date'].dt.year
    df['dayofyear'] = df['date'].dt.dayofyear
    df['dayofmonth'] = df['date'].dt.day
    df['weekofyear'] = df['date'].dt.weekofyear
    X = df.drop(['date'], axis=1)
    if target:
        y = df[target]
        X = X.drop([target], axis=1)
        return X, y

    return X


X_train_df, y_train = create_time_features(
    df_training, target='VALUES')
X_test_df, y_test = create_time_features(df_test, target='VALUES')
scaler = StandardScaler()
scaler.fit(X_train_df)  # No cheating, never scale on the training+test!
X_train = scaler.transform(X_train_df)
X_test = scaler.transform(X_test_df)

X_train_df = pd.DataFrame(X_train, columns=X_train_df.columns)
X_test_df = pd.DataFrame(X_test, columns=X_test_df.columns)

C:\Users\ggudy\AppData\Local\Temp\ipykernel_6396\2000014208.py:6: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df['date'] = df.index
C:\Users\ggudy\AppData\Local\Temp\ipykernel_6396\2000014208.py:7: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df['quarter'] = df['date'].dt.quarter
C:\Users\ggudy\AppData\Local\Temp\ipykernel_6396\2000014208.py:8: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df['month'] = df['date'].dt.month
C:\Users\ggudy\AppData\Local\Temp\ipykernel_6396\2000014208.py:9: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df['year'] = df['date'].dt.year
C:\Users\ggudy\AppData\Local\Temp\ipykernel_6396\2000014208.py:10: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df['dayofyear'] = df['date'].dt.dayofyear
C:\Users\ggudy\AppData\Local\Temp\ipykernel_6396\2000014208.py:11: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df['dayofmonth'] = df['date'].dt.day
C:\Users\ggudy\AppData\Local\Temp\ipykernel_6396\2000014208.py:12: FutureWarning: Series.dt.weekofyear and Series.dt.week have been deprecated. Please use Series.dt.isocalendar().week instead.
  df['weekofyear'] = df['date'].dt.weekofyear
C:\Users\ggudy\AppData\Local\Temp\ipykernel_6396\2000014208.py:12: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df['weekofyear'] = df['date'].dt.weekofyear
C:\Users\ggudy\AppData\Local\Temp\ipykernel_6396\2000014208.py:6: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df['date'] = df.index
C:\Users\ggudy\AppData\Local\Temp\ipykernel_6396\2000014208.py:7: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df['quarter'] = df['date'].dt.quarter
C:\Users\ggudy\AppData\Local\Temp\ipykernel_6396\2000014208.py:8: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df['month'] = df['date'].dt.month
C:\Users\ggudy\AppData\Local\Temp\ipykernel_6396\2000014208.py:9: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df['year'] = df['date'].dt.year
C:\Users\ggudy\AppData\Local\Temp\ipykernel_6396\2000014208.py:10: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df['dayofyear'] = df['date'].dt.dayofyear
C:\Users\ggudy\AppData\Local\Temp\ipykernel_6396\2000014208.py:11: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df['dayofmonth'] = df['date'].dt.day
C:\Users\ggudy\AppData\Local\Temp\ipykernel_6396\2000014208.py:12: FutureWarning: Series.dt.weekofyear and Series.dt.week have been deprecated. Please use Series.dt.isocalendar().week instead.
  df['weekofyear'] = df['date'].dt.weekofyear
C:\Users\ggudy\AppData\Local\Temp\ipykernel_6396\2000014208.py:12: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df['weekofyear'] = df['date'].dt.weekofyear


reg = RandomForestRegressor(max_depth=2, random_state=0)
reg.fit(X_train, y_train)
yhat = reg.predict(X_test)
resultsDict['Randomforest'] = evaluate(df_test.VALUES, yhat)
predictionsDict['Randomforest'] = yhat


reg = xgb.XGBRegressor(objective='reg:squarederror', n_estimators=2000)
reg.fit(X_train, y_train,
        verbose=False)  # Change verbose to True if you want to see it train
yhat = reg.predict(X_test)
resultsDict['XGBoost'] = evaluate(df_test.VALUES, yhat)
predictionsDict['XGBoost'] = yhat


plt.plot(df_test.VALUES.values, label='Original')
plt.plot(yhat, color='red', label='XGboost')
plt.legend()

<matplotlib.legend.Legend at 0x22c8d7f57c0>


models = ['Randomforest',
          'SARIMAX',
          'XGBoost',
          'ARIMA',
          'Prophet univariate',
          'HWES',
          'SES']
resis = pd.DataFrame(data={k: df_test.VALUES.values -
                     v for k, v in predictionsDict.items()})[models]
corr3 = resis.corr()
print("Residuals correlation")

Residuals correlation


sns.set_theme (style = 'white')
heatmap = sns.heatmap(corr3, annot = True)
plt.title('Relation of forecasting models') #describing relation between regression models we have tested

Text(0.5, 1.0, 'Relation of forecasting models')


resultsDict

{'SES': {'mae': 96.63231902621622,
  'rmse': 181.61570856841328,
  'mape': 262837716843.26187,
  'r2': 0.05028103465938616},
 'HWES': {'mae': 96.65029708418136,
  'rmse': 181.62303758070954,
  'mape': 262955940372.913,
  'r2': 0.0502043822324173},
 'ARIMA': {'mae': 112.50078797276525,
  'rmse': 174.8924784302066,
  'mape': 418056127030.0826,
  'r2': 0.11929480860425312},
 'AutoARIMA (4, 1, 2)': {'mae': 94.4297179004374,
  'rmse': 183.04710827623651,
  'mape': 250023568505.88513,
  'r2': 0.035251667352522276},
 'SARIMAX': {'mae': 81.4611214210943,
  'rmse': 181.9541931129425,
  'mape': 61003638790.76521,
  'r2': 0.046737676457691446},
 'Prophet univariate': {'mae': 84.195219821467,
  'rmse': 161.14071836240905,
  'mape': 164677208097.10394,
  'r2': 0.25234906183548866},
 'Randomforest': {'mae': 101.9406476255874,
  'rmse': 177.10481520958274,
  'mape': 221009006416.1009,
  'r2': 0.09687257589353537},
 'XGBoost': {'mae': 99.12256252858563,
  'rmse': 194.3084426753558,
  'mape': 148356478580.61917,
  'r2': -0.08710535217312043}}


attFrames[1]


attTimeSeRist = attFrames[1].iloc[:, [2]]
attTimeSeRist.rename(columns={'SETTORE': 'N.ATTIVATI'}, inplace=True)


attTimeSeRist


attTimeSeRist.plot()

<AxesSubplot:xlabel='DATA'>


plot_acf(attTimeSeRist)


analysis = attTimeSeRist['N.ATTIVATI'].copy()


decompose_result_mult = seasonal_decompose(analysis, model="multiplicative")

trend = decompose_result_mult.trend
seasonal = decompose_result_mult.seasonal
residual = decompose_result_mult.resid

decompose_result_mult.plot();


cwd = os.getcwd()
path = cwd + '/Ristorazione'
analysis.to_csv(path)


toStation = analysis.diff().dropna()
plt.figure(figsize=(12,5))
ax1 = toStation.plot()
ax1.set_xlabel("Date")
ax1.set_ylabel("Count")
plt.grid(True)
plt.show()


test_result=adfuller(attTimeSeRist['N.ATTIVATI'])
adfuller_test(attTimeSeRist['N.ATTIVATI'])

ADF Test Statistic : -2.100352518908367
p-value : 0.24437287550497844
#Lags Used : 2
Number of Observations : 141


attTimeSeRist['Difference'] = attTimeSeRist['N.ATTIVATI'] - attTimeSeRist['N.ATTIVATI'].shift(1)
attTimeSeRist['Seasonal First Difference']=attTimeSeRist['N.ATTIVATI']-attTimeSeRist['N.ATTIVATI'].shift(12)
attTimeSeRist.head()

C:\Users\ggudy\AppData\Local\Temp\ipykernel_6396\1124636589.py:1: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  attTimeSeRist['Difference'] = attTimeSeRist['N.ATTIVATI'] - attTimeSeRist['N.ATTIVATI'].shift(1)
C:\Users\ggudy\AppData\Local\Temp\ipykernel_6396\1124636589.py:2: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  attTimeSeRist['Seasonal First Difference']=attTimeSeRist['N.ATTIVATI']-attTimeSeRist['N.ATTIVATI'].shift(12)


adfuller_test(attTimeSeRist ['Seasonal First Difference'].dropna())

ADF Test Statistic : -1.3957124047674545
p-value : 0.5843299106614225
#Lags Used : 13
Number of Observations : 118


tfram4 = attTimeSeRist['N.ATTIVATI']


stepwise_model3 = auto_arima(tfram4, start_p=1, start_q=1,
                           max_p=3, max_q=3, m=12,
                           start_P=0, seasonal=True,
                           d=1, D=1, trace=True,
                           error_action='ignore',  
                           suppress_warnings=True, 
                           stepwise=True)
print(stepwise_model3.aic())

Performing stepwise search to minimize aic
 ARIMA(1,1,1)(0,1,1)[12]             : AIC=inf, Time=1.10 sec
 ARIMA(0,1,0)(0,1,0)[12]             : AIC=2189.130, Time=0.04 sec
 ARIMA(1,1,0)(1,1,0)[12]             : AIC=2146.605, Time=0.83 sec
 ARIMA(0,1,1)(0,1,1)[12]             : AIC=inf, Time=0.78 sec
 ARIMA(1,1,0)(0,1,0)[12]             : AIC=2175.748, Time=0.04 sec
 ARIMA(1,1,0)(2,1,0)[12]             : AIC=2127.035, Time=1.06 sec
 ARIMA(1,1,0)(2,1,1)[12]             : AIC=inf, Time=3.60 sec
 ARIMA(1,1,0)(1,1,1)[12]             : AIC=inf, Time=1.16 sec
 ARIMA(0,1,0)(2,1,0)[12]             : AIC=2140.926, Time=1.23 sec
 ARIMA(2,1,0)(2,1,0)[12]             : AIC=2107.443, Time=2.52 sec
 ARIMA(2,1,0)(1,1,0)[12]             : AIC=2116.324, Time=0.61 sec
 ARIMA(2,1,0)(2,1,1)[12]             : AIC=inf, Time=2.54 sec
 ARIMA(2,1,0)(1,1,1)[12]             : AIC=inf, Time=1.32 sec
 ARIMA(3,1,0)(2,1,0)[12]             : AIC=2106.696, Time=1.64 sec
 ARIMA(3,1,0)(1,1,0)[12]             : AIC=2113.197, Time=0.75 sec
 ARIMA(3,1,0)(2,1,1)[12]             : AIC=inf, Time=3.45 sec
 ARIMA(3,1,0)(1,1,1)[12]             : AIC=inf, Time=0.83 sec
 ARIMA(3,1,1)(2,1,0)[12]             : AIC=2105.743, Time=2.93 sec
 ARIMA(3,1,1)(1,1,0)[12]             : AIC=2113.177, Time=0.93 sec
 ARIMA(3,1,1)(2,1,1)[12]             : AIC=inf, Time=4.26 sec
 ARIMA(3,1,1)(1,1,1)[12]             : AIC=inf, Time=1.86 sec
 ARIMA(2,1,1)(2,1,0)[12]             : AIC=2107.364, Time=1.84 sec
 ARIMA(3,1,2)(2,1,0)[12]             : AIC=2107.604, Time=3.46 sec
 ARIMA(2,1,2)(2,1,0)[12]             : AIC=2109.219, Time=2.46 sec
 ARIMA(3,1,1)(2,1,0)[12] intercept   : AIC=2107.573, Time=5.43 sec

Best model:  ARIMA(3,1,1)(2,1,0)[12]          
Total fit time: 46.713 seconds
2105.7425602756894


fig = stepwise_model3.plot_diagnostics()
fig.set_size_inches(18.5, 10.5, forward=True)
plt.show()


# Train Test Split Index
train_size = 0.9
split_idx = round(len(tfram4)* train_size)
split_idx

# Split
train3 = tfram4.iloc[:split_idx]
test3 = tfram4.iloc[split_idx:]

# Visualize split
fig,ax= plt.subplots(figsize=(12,8))
kws = dict(marker='o')
plt.plot(train3, label='Train', **kws)
plt.plot(test3, label='Test', **kws)
ax.legend(bbox_to_anchor=[1,1]);


stepwise_model3.fit(train3)

ARIMA(order=(3, 1, 1), scoring_args={}, seasonal_order=(2, 1, 0, 12),
      suppress_warnings=True, with_intercept=False)


future2, cf3 = stepwise_model3.predict(n_periods=14, return_conf_int=True)


future2 = pd.DataFrame(future2,index = test3.index, columns=['Prediction'])


cc = pd.concat([test3,future2],axis=1)
cc.plot(**kwsnep, figsize=(20, 10))

<AxesSubplot:xlabel='DATA'>


index_of2 = pd.date_range(tfram4.index[-1], periods = 14, freq='MS')

f = future2
f = f.set_index(index_of2)

# Plot Della prediction 
plt.figure(figsize=(25, 15))
plt.plot(tfram4, color='blue', label='Actual Date', **kwsn)
plt.plot(f, color='red', label='Predict', **kwsn)
plt.legend(loc='lower right', fontsize=15)
plt.title("Predizione cessati")
plt.show()


mape = mean_absolute_percentage_error(test3, f.Prediction)
print(mape)

0.3430122514976612


MSE = mean_squared_error(test3, f)
RMSE = math.sqrt(MSE)
print('The mean square error is: ', MSE)
print('The Root Mean Square error is: ', RMSE)

The mean square error is:  1002977.8325520398
The Root Mean Square error is:  1001.4878094874844

	Anno	Regioni	P.I.L. Milioni di Euro
0	2000-01-01	Emilia Romagna	106154
1	2000-01-01	Lazio	138118
2	2000-01-01	Lombardia	259861
3	2000-01-01	Piemonte	99693
4	2000-01-01	Veneto	111462
...	...	...	...
100	2020-01-01	Lazio	186298
101	2020-01-01	Lombardia	365515
102	2020-01-01	Piemonte	126199
103	2020-01-01	Veneto	151910
104	2021-01-01	Lombardia	391101

	Anno	Regioni	P.I.L. Milioni di Euro
0	2000-01-01	Emilia Romagna	106154
1	2000-01-01	Lazio	138118
2	2000-01-01	Lombardia	259861
3	2000-01-01	Piemonte	99693
4	2000-01-01	Veneto	111462
5	2001-01-01	Emilia Romagna	110741
6	2001-01-01	Lazio	146723
7	2001-01-01	Lombardia	273359
8	2001-01-01	Piemonte	104026
9	2001-01-01	Veneto	115853

	Anno	P.I.L. Milioni di Euro
2	2000-01-01	259861
7	2001-01-01	273359
12	2002-01-01	285312
17	2003-01-01	294774
22	2004-01-01	304987
27	2005-01-01	313488
32	2006-01-01	323238
37	2007-01-01	336926
42	2008-01-01	349924
47	2009-01-01	334011
52	2010-01-01	349558
57	2011-01-01	357748
62	2012-01-01	351390
67	2013-01-01	348117
72	2014-01-01	355347
77	2015-01-01	362330
82	2016-01-01	373038
87	2017-01-01	383033
91	2018-01-01	393500
96	2019-01-01	397507
101	2020-01-01	365515
104	2021-01-01	391101

	P.I.L. Milioni di Euro
Anno
2000	259861
2001	273359
2002	285312
2003	294774
2004	304987
2005	313488
2006	323238
2007	336926
2008	349924
2009	334011
2010	349558
2011	357748
2012	351390
2013	348117
2014	355347
2015	362330
2016	373038
2017	383033
2018	393500
2019	397507
2020	365515
2021	391101

	DATA	GENERE	ETA	SETTOREECONOMICODETTAGLIO	TITOLOSTUDIO	CONTRATTO	MODALITALAVORO	PROVINCIAIMPRESA	ITALIANO
0	2020-05-09	F	60	Attività di famiglie e convivenze come datori ...	NESSUN TITOLO DI STUDIO	LAVORO DOMESTICO	TEMPO PIENO	BERGAMO	UCRAINA
1	2019-07-12	M	43	Gestioni di funicolari, ski-lift e seggiovie s...	LICENZA MEDIA	LAVORO A TEMPO DETERMINATO	TEMPO PIENO	BERGAMO	ITALIA
2	2013-06-05	F	20	Fabbricazione di altre apparecchiature elettri...	LICENZA MEDIA	APPRENDISTATO PROFESSIONALIZZANTE O CONTRATTO ...	TEMPO PIENO	BERGAMO	ITALIA
3	2010-03-12	F	28	Alberghi	DIPLOMA DI ISTRUZIONE SECONDARIA SUPERIORE CH...	LAVORO INTERMITTENTE A TEMPO DETERMINATO	NON DEFINITO	BERGAMO	ITALIA
4	2021-04-06	F	49	Rifugi di montagna	LICENZA MEDIA	LAVORO INTERMITTENTE	NON DEFINITO	BERGAMO	ITALIA
...	...	...	...	...	...	...	...	...	...
9579789	2020-03-01	M	52	Lavori di meccanica generale	LICENZA MEDIA	LAVORO A TEMPO DETERMINATO	TEMPO PIENO	BERGAMO	ITALIA
9579790	2010-09-06	M	61	Lavori di meccanica generale	NESSUN TITOLO DI STUDIO	LAVORO A TEMPO INDETERMINATO	TEMPO PIENO	BERGAMO	ALBANIA
9579791	2021-11-06	M	37	Fabbricazione di parti ed accessori per bicicl...	NESSUN TITOLO DI STUDIO	LAVORO A TEMPO DETERMINATO	TEMPO PIENO	BERGAMO	SENEGAL
9579792	2010-02-02	M	35	Fabbricazione di parti ed accessori per bicicl...	LICENZA MEDIA	LAVORO INTERINALE (O A SCOPO DI SOMMINISTRAZIO...	TEMPO PIENO	BERGAMO	SENEGAL
9579793	2012-07-05	F	39	Commercio all'ingrosso di abbigliamento e acce...	LICENZA MEDIA	LAVORO INTERINALE (O A SCOPO DI SOMMINISTRAZIO...	NaN	BERGAMO	ITALIA

	DATE	GENERE	ETA	SETTORE	CONTRATTO	STATO	MESE	ANNO	PIL MLN EUR ANNUO	SETT_ID	CONTR_N
DATA
2000-01-07	2000-01-07	1	38	Attività di famiglie e convivenze come datori ...	LAVORO DOMESTICO A TEMPO INDETERMINATO	0	1	2000	259861	188	34
2000-02-03	2000-02-03	1	42	Attività di famiglie e convivenze come datori ...	LAVORO DOMESTICO A TEMPO INDETERMINATO	0	2	2000	259861	188	34
2000-03-01	2000-03-01	0	46	Attività di famiglie e convivenze come datori ...	LAVORO DOMESTICO A TEMPO INDETERMINATO	0	3	2000	259861	188	34
2000-09-06	2000-09-06	0	31	Attività di famiglie e convivenze come datori ...	LAVORO DOMESTICO A TEMPO INDETERMINATO	0	9	2000	259861	188	34
2000-11-09	2000-11-09	0	58	Attività di famiglie e convivenze come datori ...	LAVORO DOMESTICO A TEMPO INDETERMINATO	0	11	2000	259861	188	34

	CONTRATTO	CONTR_N	SETTORE	SETT_ID	STATO	ETA	GENERE	DATE	MESE	ANNO	PIL MLN EUR ANNUO
DATA
2010-01-01	LAVORO A DOMICILIO A TEMPO INDETERMINATO	23	Preparazione e filatura di fibre tessili	965	0	60	0	2010-01-01	1	2010	349558
2010-01-01	LAVORO A TEMPO DETERMINATO	25	Raccolta e depurazione delle acque di scarico	1046	0	36	1	2010-01-01	1	2010	349558
2010-01-01	LAVORO A TEMPO INDETERMINATO	27	Bar e altri esercizi simili senza cucina	235	0	36	1	2010-01-01	1	2010	349558
2010-01-01	LAVORO A TEMPO DETERMINATO	25	Trasporto di merci su strada	1203	0	31	1	2010-01-01	1	2010	349558
2010-01-01	LAVORO A TEMPO INDETERMINATO	27	Agenti di assicurazioni	5	0	52	0	2010-01-01	1	2010	349558
...	...	...	...	...	...	...	...	...	...	...	...
2021-12-09	LAVORO DOMESTICO	32	Attività di famiglie e convivenze come datori ...	188	0	45	0	2021-12-09	12	2021	391101
2021-12-09	LAVORO A TEMPO INDETERMINATO	27	Servizi logistici relativi alla distribuzione ...	1170	0	46	1	2021-12-09	12	2021	391101
2021-12-09	LAVORO A TEMPO DETERMINATO	25	Coltivazione di ortaggi(inclusi i meloni) in f...	262	0	52	1	2021-12-09	12	2021	391101
2021-12-09	LAVORO A TEMPO INDETERMINATO	27	Servizi logistici relativi alla distribuzione ...	1170	0	25	0	2021-12-09	12	2021	391101
2021-12-09	LAVORO A TEMPO INDETERMINATO	27	Servizi logistici relativi alla distribuzione ...	1170	0	39	1	2021-12-09	12	2021	391101

	ATTIVAZIONI	CESSAZIONI
SETTORE
Alberghi	437403	61989
Ristorazione con somministrazione	424929	202637
Attività di produzione cinematografica, di video e di programmi televisivi	355267	7561
Attività di famiglie e convivenze come datori di lavoro per personale domestico	326150	258683
Altri servizi di supporto alle imprese nca	281581	143166
Pulizia generale (non specializzata) di edifici	252967	145277
Istruzione secondaria di primo grado: scuole medie	249435	21910
Costruzione di edifici residenziali e non residenziali	223083	171079
Commercio al dettaglio di confezioni per adulti	157768	32198
Istruzione primaria: scuole elementari	156582	12745

	Alberghi	Ristorazione con somministrazione	Attività di produzione cinematografica, di video e di programmi televisivi	Attività di famiglie e convivenze come datori di lavoro per personale domestico	Altri servizi di supporto alle imprese nca	Pulizia generale (non specializzata) di edifici	Istruzione secondaria di primo grado: scuole medie	Costruzione di edifici residenziali e non residenziali	Commercio al dettaglio di confezioni per adulti	Istruzione primaria: scuole elementari
2010	47362	24097	22961	31641	38878	19373	16154	19756	6493	15938
2011	48194	26522	24920	25846	34991	22127	17132	21044	7759	15755
2012	38889	30406	22053	26468	36275	21870	17382	17602	12108	15693
2013	36996	26102	24273	28872	28722	17394	22118	17408	8736	14817
2014	36281	31617	27560	24748	25211	16518	24831	16723	10391	14408
2015	39300	35944	29257	22784	19581	19763	25440	17901	12554	13630
2016	37828	34756	33961	22523	16415	20997	20389	17840	21416	10696
2017	42149	49113	33412	22407	19134	23292	20050	18414	23463	10799
2018	43396	52870	37154	24155	20552	25800	21241	19549	18537	11187
2019	43733	56466	37965	25210	18091	27254	24585	19356	15031	12291
2020	10960	27853	29759	48704	12367	19223	21547	17969	10138	11044
2021	12315	29183	31992	22792	11364	19356	18566	19521	11142	10324

	Attività di famiglie e convivenze come datori di lavoro per personale domestico	Ristorazione con somministrazione	Costruzione di edifici residenziali e non residenziali	Pulizia generale (non specializzata) di edifici	Altri servizi di supporto alle imprese nca	Trasporto di merci su strada	Bar e altri esercizi simili senza cucina	Servizi logistici relativi alla distribuzione delle merci	Alberghi	Movimento merci relativo ad altri trasporti terrestri
2010	15325	13935	20432	13508	19072	6449	8357	2035	6312	5698
2011	21642	15492	20954	14145	17960	7300	8958	3983	7792	5401
2012	25292	18403	17682	13978	15784	7008	9804	5011	6368	5610
2013	24870	16707	15620	13388	14512	6651	8339	5285	6292	4590
2014	22037	16379	14049	10847	12414	6471	7221	6253	6111	4829
2015	21551	16796	13906	12693	13120	6695	6072	5514	5655	5342
2016	20289	16232	12639	11356	11460	6264	5801	5978	3892	4019
2017	21606	18369	12740	10889	8421	7452	6581	6139	4134	4636
2018	22192	20816	12773	11730	9932	8261	7503	6124	4750	4250
2019	21743	22227	12366	13772	9615	9374	7580	9314	5163	6027
2020	23392	15686	8692	10914	6123	6988	5161	7266	3776	3470
2021	18744	11595	9226	8057	4753	7181	3920	6297	1744	2953

	N.ATTIVATI	Difference	Seasonal First Difference
DATA
2010-01-31	61434	NaN	NaN
2010-02-28	55401	-6033.0	NaN
2010-03-31	57889	2488.0	NaN
2010-04-30	57900	11.0	NaN
2010-05-31	59538	1638.0	NaN

	N.CESSATI	Difference	Seasonal First Difference
DATA
2010-01-31	52120	NaN	NaN
2010-02-28	44051	-8069.0	NaN
2010-03-31	31956	-12095.0	NaN
2010-04-30	37181	5225.0	NaN
2010-05-31	26362	-10819.0	NaN

	N.ATTIVATI
DATA
2010-01-31	2254
2010-02-28	2139
2010-03-31	1869
2010-04-30	1867
2010-05-31	2054
...	...
2021-08-31	2016
2021-09-30	2401
2021-10-31	2467
2021-11-30	2042
2021-12-31	1796